Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning
Jia Wang, Yawen Li, Yingxia Shao, Zhe Xue, Zeli Guan, Ang Li, Guanhua Ye
Abstract
Carefully selecting clients to participate in aggregation can assist the global model in achieving better performance. However, existing research on federated heterogeneous graph learning (FHGL) has shown limited attention to the client selection (CS) problem. Current CS algorithms face challenges in accurately evaluating client contributions and selecting appropriate participants in the context of FHGL, leading to a dilemma between convergence and accuracy. In this paper, we propose a Reinforcement Active client selection based Federated Heterogeneous Graph Learning (RAFHGL), which precisely evaluates the importance of local heterogeneous graph data and selects high-contributing clients for aggregation. RAFHGL employs an active learning agent to select representative nodes for local training. The statistical features of the active scores are used to assess client contributions. A client selection agent then chooses clients conducive to global model convergence for aggregation. To address heterogeneity introduced by sample and client selection, the training process stabilizes by correcting local losses based on data prototypes. Experimental results on 4 publicly available heterogeneous graph datasets show that RAFHGL outperforms existing Client Selection algorithms in federated heterogeneous graph learning scenarios in terms of performance and convergence.
BibTeX
@article{Wang_Li_Shao_Xue_Guan_Li_Ye_2025, title={Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35409}, DOI={10.1609/aaai.v39i20.35409}, abstractNote={Carefully selecting clients to participate in aggregation can assist the global model in achieving better performance. However, existing research on federated heterogeneous graph learning (FHGL) has shown limited attention to the client selection (CS) problem. Current CS algorithms face challenges in accurately evaluating client contributions and selecting appropriate participants in the context of FHGL, leading to a dilemma between convergence and accuracy. In this paper, we propose a Reinforcement Active client selection based Federated Heterogeneous Graph Learning (RAFHGL), which precisely evaluates the importance of local heterogeneous graph data and selects high-contributing clients for aggregation. RAFHGL employs an active learning agent to select representative nodes for local training. The statistical features of the active scores are used to assess client contributions. A client selection agent then chooses clients conducive to global model convergence for aggregation. To address heterogeneity introduced by sample and client selection, the training process stabilizes by correcting local losses based on data prototypes. Experimental results on 4 publicly available heterogeneous graph datasets show that RAFHGL outperforms existing Client Selection algorithms in federated heterogeneous graph learning scenarios in terms of performance and convergence.}, number={20}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Jia and Li, Yawen and Shao, Yingxia and Xue, Zhe and Guan, Zeli and Li, Ang and Ye, Guanhua}, year={2025}, month={Apr.}, pages={21117-21125} }